Interpretation of Deep CNN Based on Learning Feature Reconstruction With Feedback Weights

Islam, Naeem Ul; Lee, Sukhan

doi:10.1109/access.2019.2899901

Cited by 19 publications

(14 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As discussed above, 2D features can be regarded as gray scale images, since the neural network perceive a 2D input from value of each pixel not the object in human cognition. Therefore, a lot of saliency detection methods used in image processing, like LRP, input cropping, deconvolution, and gradient algorithms [16] can be also applied in SEI. Image-specific class saliency visualization (ISCSV), an effective saliency detection technique based on gradient algorithm, is the theoretical basis of our proposed method.…”

Section: Mc-featurementioning

confidence: 99%

“…Based on successful applications of ISCSV in saliency detection, it is considered that the inner recognition mechanism can probably be reflected by ISCSV. As mentioned in Section 1, various transformed features with 2 dimension can be regarded as an equivalent to the input in Equation (16). In the beginning of forward propagation of CNN, each pixel in 2D transformed feature is perceived by different convolutional kernel.…”

Section: Saliency Mapmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Data-Driven Specific Emitter Identification Feature Based on Machine Cognition

2020

View full text Add to dashboard Cite

Machine learning becomes increasingly promising in specific emitter identification (SEI), particularly in feature extraction and target recognition. Traditional features, such as radio frequency (RF), pulse amplitude (PA), power spectral density (PSD), and etc., usually show limited recognition effects when only a slight difference exists in radar signals. Numerous two-dimensional features on transform domain, like various time-frequency representation and ambiguity function are used to augment information abundance, whereas the unacceptable computational burden usually emerges. To solve this problem, some artfully handcrafted features in transformed domain are proposed, like representative slice of ambiguity function (AF-RS) and compressed sensing mask (CS-MASK), to extract representative information that contributes to machine recognition task. However, most handcrafted features only utilizing neural network as a classifier, few of them focus on mining deep informative features from the perspective of machine cognition. Such feature extraction that is based on human cognition instead of machine cognition may probably miss some seemingly nominal texture information which actually contributes greatly to recognition, or collect too much redundant information. In this paper, a novel data-driven feature extraction is proposed based on machine cognition (MC-Feature) resort to saliency detection. Saliency detection exhibits positive contributions and suppresses irrelevant contributions in a transform domain with the help of a saliency map calculated from the accumulated gradients of each neuron to input data. Finally, positive and irrelevant contributions in the saliency map are merged into a new feature. Numerous experimental results demonstrate that the MC-feature can greatly strengthen the slight intra-class difference in SEI and provides a possibility of interpretation of CNN.

show abstract

Section: Mc-featurementioning

confidence: 99%

Section: Saliency Mapmentioning

confidence: 99%

A Novel Data-Driven Specific Emitter Identification Feature Based on Machine Cognition

2020

View full text Add to dashboard Cite

show abstract

“…Within-domain image translation has applications in domain adaptation [1]- [6], super-resolution [7], style transfer [8], and photo editing [9], Target and anomaly detection [10]- [13], and cross-domain image translation has applications in data generation [14], data interpretation [15], transformation of 3D images to their corresponding 3D representation for interpretation of deep CNN [16], and image completion [15], [17], [18]. The availability of a large amount of paired data for image translation makes convolutional neural network (CNN) approaches to regression highly attractive for both within-and cross-domain image translation, surpassing the performance of the state-of-the-art non-CNN approaches [19], [20].…”

Section: Related Workmentioning

confidence: 99%

Robust Image Translation and Completion Based on Dual Auto-Encoder With Bidirectional Latent Space Regression

Lee

Islam

2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

Automated image translation and completion is a subject of keen interest due to their impact on image representation, interpretation, and enhancement. To date, a conditional or a dual adversarial framework with a convolutional auto-encoder embedded as a generator is known to offer the best accuracy in image translation. However, although the frequency is excellent, the adversarial framework may suffer from a lack of generality, i.e., the accuracy drops when translating incomplete and corrupted data given as untrained noisy input data. This paper proposes an approach to robust image-to-image translation that offers a high level of generality while keeping accuracy high as well. The proposed approach is referred to here as a dual autoencoder with bidirectional latent space regression or Bi-directionally Associative DualAE, for short. The proposed BA-DualAE is configured with two auto-encoders the individual latent spaces of which are tightly associated by a bidirectional regression network. Once the two auto-encoders are trained independently for their respective domains, and then, the bidirectional regression network is trained to learn the general association between data pairs. With its capability of robust and bidirectional image translation, BA-DualAE performed direct image completion with no iterative search. The experiments with photo-sketch datasets demonstrated that the proposed BA-DualAE is highly robust under incomplete or corrupted data conditions and is far superior to adversarial frameworks in terms of generality and robustness.INDEX TERMS Convolutional neural network, auto-encoder, bidirectional latent space regression, imageto-image translation, generative adversarial network.

show abstract

“…The image-to-image translation problem is related to either computer vision, where the mapping is from many to one, or computer graphics, where the mapping is from one to many. Despite the similar nature of these tasks, they have been tackled separately by [1][2][3][4][5][6][7][8][9][10][11][12][13]. However, in our approach, we tackled this in a unified framework.…”

Section: Introductionmentioning

confidence: 99%

Accurate and Consistent Image-to-Image Conditional Adversarial Network

2020

Self Cite

View full text Add to dashboard Cite

Image-to-image translation based on deep learning has attracted interest in the robotics and vision community because of its potential impact on terrain analysis and image representation, interpretation, modification, and enhancement. Currently, the most successful approach for generating a translated image is a conditional generative adversarial network (cGAN) for training an autoencoder with skip connections. Despite its impressive performance, it has low accuracy and a lack of consistency; further, its training is imbalanced. This paper proposes a balanced training strategy for image-to-image translation, resulting in an accurate and consistent network. The proposed approach uses two generators and a single discriminator. The generators translate images from one domain to another. The discriminator takes the input of three different configurations and guides both the generators to generate realistic images in their corresponding domains while ensuring high accuracy and consistency. Experiments are conducted on different datasets. In particular, the proposed approach outperforms the cGAN in realistic image translation in terms of accuracy and consistency in training.

show abstract

Interpretation of Deep CNN Based on Learning Feature Reconstruction With Feedback Weights

Cited by 19 publications

References 22 publications

A Novel Data-Driven Specific Emitter Identification Feature Based on Machine Cognition

A Novel Data-Driven Specific Emitter Identification Feature Based on Machine Cognition

Robust Image Translation and Completion Based on Dual Auto-Encoder With Bidirectional Latent Space Regression

Accurate and Consistent Image-to-Image Conditional Adversarial Network

Contact Info

Product

Resources

About